Supervised classification of satellite images

Remote sensing is the method used to detect and measure target characteristics using electromagnetic energy in the form of heat, light and radio waves. Different applications where remote sensing is used are agriculture, disaster management, urban planning, water resource management, etc. The process of producing thematic map from remotely sensed imagery is called image classification. In one or more spectral bands digital numbers are used to represent spectral information. This information is used for digital image classification. Individual pixels are classified using this spectral information. For classification multispectral satellite images are used. Image classification can be supervised and unsupervised. The paper deals with the supervised classifiers namely minimum distance,support vector machine, maximum likelihood, and parallelepiped. The performance of these classifiers is judged on the basis of kappa coefficient and overall accuracy.